Embeddings: What they are and why they matter

Extensive notes to accompany this talk: simonwillison.net/2023/Oct/23...

[@Clammer999]

I’m totally new to embeddings and this video inspired me to want learn even more!

[@nursenayeneredit7251]

These 38 minutes changed my next 38 years

[@technicolourmyles]

How so? I'm still at the beginning

[@martinjohnpeck]

This has been a timely and really useful presentation. Thank you for posting it!

[@_ramen]

very great demo, thanks for sharing!
this is an excellent example of practical use of embeddings.

[@thanhquachable]

Thanks Simon for sharing your knowledge. This video is so underrated.

[@zgintasz2]

"vibes-based search" lol. love the term you invented.

[@sebastianwagner5843]

Things start to become magical.

[@loicleray]

That was awesome. Thank you for uploading it!

[@donpark2832]

Great talk. Thoroughly enjoyed it. Thanks!

[@user-yg3io9mu1m]

A nice and very inspiring presentation! Thank you!

[@brandonbennett7851]

Brilliant!!! (as always)

Great talk. Very interesting subject.

[@curtisblake261]

Impressive fast talking and fast scrolling. A lot of knowledge and experience for sure. I guess I'll have to do some digging if I want to really benefit from this lecture.

[@vmstanford]

Great work! I will definitely follow up on your website. Some of the clustering results are really remarkable. Have you thought about hierarchal clustering on the embeddings to see if a sensible taxonomy emerges?

[@rileydavidjesus]

What a genius

[@miikalewandowski7765]

How does the semantic vectorization of a word look like, in a mathematical sense ? Is it like every word has it’s spatial ID (coordinate) and gets kind of multiplied with a vector array of assoziatives IDs?

[@BuFu1O1]

damn!!!

[@BuFu1O1]

Can you show us some Imagebind unix-fu?

[@asiddiqi123]

Why are you wearing a mask 😷?

[@KayButtonJay]

Maybe he doesn’t want to get people sick genius